In several video surveillance applications, such as the detection of abandoned/stolen objects or parked vehicles, the detection of stationary foreground objects is a critical task. In this paper the model based framework is suggested for detecting static objects. Firstly, a background subtraction based method that relies on modeling not only the background, but also the stopped foreground is implemented. Secondly, selforganizing model for image sequences which automatically adapts to scene changes is performed. Finally, we evaluate the proposed algorithm and compare results with the background segmentation algorithm using video surveillance sequences from visor datasets. Experimental results show that the proposed approach has better detection accuracy of stationary foreground regions as compared to the segmentation approach.